Prediction of Resilient Modulus of Asphalt Pavement Material Using Support Vector Machine

The purpose of this paper is to simulate the resilient modulus of asphalt pavement material using support vector machines(SVM).First, selecting 15 training datasets randomly and remaining 9 testing datasets to create model, then radial basis function kernel and polynomial kernel based on support vector machines are used to simulate the resilient modulus. The correlation coefficients values were achieved by radial basis function kernel and polynomial kernel based on support vector machines. The result of sensitive analysis among input parameters such as P_4.75, P_2.36, P_0.075, V_a, P_b shows that the parameter P_b has maximum influence on resilient modulus. The predicting results indicate that the proposed SVM model can gain higher precision than artificial neural network approach and multiple regression, which provides a new way for predicting resilient modulus and other mechanical behaviour index of asphalt pavement material.